A look at the original data provided

import pandas as pd
df = pd.read_csv("/data/workspace_files/2021 Data/202109-divvy-tripdata.csv")

df.head()

df.describe()

df.isnull().sum()

df1=pd.read_csv("/data/workspace_files/2020 Data/202010-divvy-tripdata.csv")
df1.head()

df1.describe()

df1.isnull().sum()

df1.dtypes

newdata=pd.concat([df, df1])
newdata.describe()

df=pd.read_csv("/data/workspace_files/2020 Data/202012-divvy-tripdata.csv")
df.head(3)

df.describe()

df.dtypes

df.start_station_id.unique()

df.isnull().sum()

df.start_lat.nunique()

df.member_casual.value_counts()

df.rideable_type.value_counts()

casual=df[df.member_casual == 'casual']
casual.head()

casual.isnull().sum()

Q420=pd.concat([newdata, df])
Q420.head()

Q420.describe()

Q420.to_csv("/data/workspace_files/2020 Data/Q42020.csv")

import plotly.express as px
df=pd.read_csv("/data/workspace_files/2020 Data/Q42020.csv")
df.head()

df.start_station_id = df.start_station_id.astype(str)

df.end_station_id = df.end_station_id.astype(str)

df.dtypes

df.to_csv("/data/workspace_files/2020 Data/Q42020.csv")

df=pd.read_csv("/data/workspace_files/2020 Data/Q42020.csv")
df.drop(columns=["Unnamed: 0", "Unnamed: 0.1"], inplace=True)
df.head()

df.drop(columns=["Unnamed: 0", "Unnamed: 0.1"], inplace=True)
df.head()

df.dtypes

members=df.groupby(df.rideable_type)